© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56798
    Prev
    Next
    INDEX
    Explanations

    originates or results in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    argon
    -0.09
     influences
    -0.09
     influencing
    -0.08
    uguay
    -0.08
     possibly
    -0.08
    umbo
    -0.08
    ango
    -0.08
     Tanner
    -0.08
     app
    -0.08
    /on
    -0.08
    POSITIVE LOGITS
     began
    0.09
     originated
    0.09
    illy
    0.09
     originally
    0.08
     Originally
    0.08
     accompanied
    0.08
    pis
    0.08
     genom
    0.08
     begun
    0.08
     debuted
    0.08
    Activations Density 0.106%

    No Known Activations